Multi-Horizon Predictive Soil Mapping of Historical Soil Properties Using Remote Sensing Imagery

• Published in: Remote sensing (Basel, Switzerland) Switzerland), 2022-11, Vol.14 (22), p.5803
• Main Authors: Sorenson, Preston T., Kiss, Jeremy, Bedard-Haughn, Angela K., Shirtliffe, Steve
• Format: Article
• Language: English
• Subjects: Agriculture; bare soil composite imagery; Carbon; Carbon content; Cation exchange; Cation exchanging; Clay; Climatic data; Electrical conductivity; Electrical resistivity; Imagery; Inorganic carbon; Land use; Land use management; Land use planning; Mapping; Mean square errors; multi-temporal remote sensing; Nitrogen; Organic carbon; Organic soils; Precision farming; Prediction models; predictive soil mapping; random forest; Remote sensing; Sand; Saskatchewan; Soil horizons; Soil mapping; Soil maps; Soil properties
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs14225803

There is increasing demand for more detailed soil maps to support fine-scale land use planning, soil carbon management, and precision agriculture in Saskatchewan. Predictive soil mapping that incorporates a combination of environmental covariates provides a cost-effective tool for generating finer resolution soil maps. This study focused on mapping soil properties for multiple soil horizons in Saskatchewan using historical legacy soil data in combination with remote sensing band indices, bare soil composite imagery, climate data, and terrain attributes. Mapped soil properties included soil organic carbon content (SOC), total nitrogen, cation exchange capacity (CEC), electrical conductivity (EC), inorganic carbon (IOC), sand and clay content, and total profile soil organic carbon stocks. For each of these soil properties, a recursive feature elimination was undertaken to reduce the number of features in the overall model. This process involved iteratively removing features such that random forest out-of-bag error was minimized. Final random forest models were built for each property and evaluated using an independent test dataset. Overall, predictive models were successful for SOC (R2 = 0.71), total nitrogen (R2 = 0.65), CEC (R2 = 0.46), sand content (R2 = 0.44) and clay content (R2 = 0.55). The methods used in this study enable mapping of a greater geographic region of Saskatchewan compared to those previously established that relied solely on bare soil composite imagery.